Day 1:はじめてのオープンデータ処理（１）

if(!require(ggplot2)){　# 拡張パッケージはインストールされているか？
  # 拡張パッケージのインストール
  install.packages("ggplot2")
  # 拡張パッケージの読み込み
  library(ggplot2)
}

## Loading required package: ggplot2

if(!require(pdftools)){　# 拡張パッケージはインストールされているか？
  # 拡張パッケージのインストール
  install.packages("pdftools")
  # 拡張パッケージの読み込み
  library(pdftools)
}

## Loading required package: pdftools

if(!require(plotflow)){
devtools::install_github("trinker/plotflow")
library(plotflow)
}

## Loading required package: plotflow

if(.Platform$OS.type=="windows")
  windowsFonts(yugo=windowsFont("Yu Gothic"))
if(capabilities("aqua"))
  quartzFonts(yugo=quartzFont(rep("YuGo-Medium",4)))


url = "http://www.hit-u.ac.jp/guide/information/data/pdf/06_kakenhi_2016.pdf"
url = "day03/06_kakenhi_2016.pdf"
res <- pdf_text(url)
#res<-iconv(res[1],to="UTF-8")
res<-gsub(",","",res[1])
res<-gsub(" +",",",res[1])
df16<-read.csv(text=res[1],skip = 5,header = FALSE,stringsAsFactors = FALSE)
df16<-df16[-(13:nrow(df16)),]

df16$V2[is.na(df16$V2)]<-0
df16$V3[is.na(df16$V3)]<-0
df16$V4[is.na(df16$V4)]<-0


df16$V2<-as.numeric(df16$V2)
df16$V3<-as.numeric(df16$V3)
df16$V4<-as.numeric(df16$V4)
g1<-ggplot(df16,aes(x=V1,y=V2))+geom_bar(stat="identity")+xlab("研究種目")+ylab("交付件数")+theme_gray(base_family ="yugo")+theme(axis.text.x = element_text(angle = 90, hjust = 1),plot.margin = grid::unit(c(.5, 1, .5, 0), "cm"))
g1

g2<-ggplot(df16,aes(x=V1,y=(V3+V4)/10000,group=1))+geom_line(colour = "magenta",linetype = 2,size = 0.5 )+xlab("研究種目")+ylab("交付額（万円）")+theme_bw(base_family ="yugo")+theme(axis.text.x = element_text(angle = 90, hjust = 1),plot.margin = grid::unit(c(.5, 1, .5, 0), "cm"),panel.grid.major = element_blank(),panel.grid.minor = element_blank(),panel.background = element_blank())
g2

ggdual_axis(lhs = g1, rhs = g2)

url = "http://www.hit-u.ac.jp/guide/information/data/pdf/06_kakenhi_2015.pdf"
url = "day03/06_kakenhi_2015.pdf"
res <- pdf_text(url)
#res<-iconv(res[1],to="UTF-8")
res<-gsub(",","",res[1])
res<-gsub(" +",",",res[1])
df15<-read.csv(text=res[1],skip = 5,header = FALSE,stringsAsFactors = FALSE)
df15<-df15[-(12:nrow(df15)),]

df15$V2[is.na(df15$V2)]<-0
df15$V3[is.na(df15$V3)]<-0
df15$V4[is.na(df15$V4)]<-0

df15$V2<-as.numeric(df15$V2)
df15$V3<-as.numeric(df15$V3)
df15$V4<-as.numeric(df15$V4)
g1<-ggplot(df15,aes(x=V1,y=V2))+geom_bar(stat="identity")+xlab("研究種目")+ylab("交付件数")+theme_gray(base_family ="yugo")+theme(axis.text.x = element_text(angle = 90, hjust = 1),plot.margin = grid::unit(c(.5, 1, .5, 0), "cm"))
g1

g2<-ggplot(df15,aes(x=V1,y=(V3+V4)/10000,group=1))+geom_line(colour = "magenta",linetype = 2,size = 0.5 )+xlab("研究種目")+ylab("交付額（万円）")+theme_bw(base_family ="yugo")+theme(axis.text.x = element_text(angle = 90, hjust = 1),plot.margin = grid::unit(c(.5, 1, .5, 0), "cm"),panel.grid.major = element_blank(),panel.grid.minor = element_blank(),panel.background = element_blank())
g2

ggdual_axis(lhs = g1, rhs = g2)

url = "http://www.hit-u.ac.jp/guide/information/data/pdf/06_kakenhi_2014.pdf"
url = "day03/06_kakenhi_2014.pdf"
res <- pdf_text(url)
#res<-iconv(res[1],to="UTF-8")
res<-gsub(",","",res[1])
res<-gsub(" +",",",res[1])
df14<-read.csv(text=res[1],skip = 5,header = FALSE,stringsAsFactors = FALSE)
df14<-df14[-(13:nrow(df14)),]

df14$V2[is.na(df14$V2)]<-0
df14$V3[is.na(df14$V3)]<-0
df14$V4[is.na(df14$V4)]<-0

df14$V2<-as.numeric(df14$V2)
df14$V3<-as.numeric(df14$V3)
df14$V4<-as.numeric(df14$V4)
g1<-ggplot(df14,aes(x=V1,y=V2))+geom_bar(stat="identity")+xlab("研究種目")+ylab("交付件数")+theme_gray(base_family ="yugo")+theme(axis.text.x = element_text(angle = 90, hjust = 1),plot.margin = grid::unit(c(.5, 1, .5, 0), "cm"))
g1

## Warning: Removed 1 rows containing missing values (position_stack).

g2<-ggplot(df14,aes(x=V1,y=(V3+V4)/10000,group=1))+geom_line(colour = "magenta",linetype = 2,size = 0.5 )+xlab("研究種目")+ylab("交付額（万円）")+theme_bw(base_family ="yugo")+theme(axis.text.x = element_text(angle = 90, hjust = 1),plot.margin = grid::unit(c(.5, 1, .5, 0), "cm"),panel.grid.major = element_blank(),panel.grid.minor = element_blank(),panel.background = element_blank())
g2

ggdual_axis(lhs = g1, rhs = g2)

## Warning: Removed 1 rows containing missing values (position_stack).

url = "http://www.hit-u.ac.jp/guide/information/data/pdf/06_kakenhi_2013.pdf"
url = "day03/06_kakenhi_2013.pdf"
res <- pdf_text(url)
#res<-iconv(res[1],to="UTF-8")
res<-gsub(",","",res[1])
res<-gsub(" +",",",res[1])
df13<-read.csv(text=res[1],skip = 5,header = FALSE,stringsAsFactors = FALSE)
df13<-df13[-(13:nrow(df13)),]

df13$V2[is.na(df13$V2)]<-0
df13$V3[is.na(df13$V3)]<-0
df13$V4[is.na(df13$V4)]<-0

df13$V2<-as.numeric(df13$V2)
df13$V3<-as.numeric(df13$V3)
df13$V4<-as.numeric(df13$V4)
g1<-ggplot(df13,aes(x=V1,y=V2))+geom_bar(stat="identity")+xlab("研究種目")+ylab("交付件数")+theme_gray(base_family ="yugo")+theme(axis.text.x = element_text(angle = 90, hjust = 1),plot.margin = grid::unit(c(.5, 1, .5, 0), "cm"))
g1

g2<-ggplot(df13,aes(x=V1,y=(V3+V4)/10000,group=1))+geom_line(colour = "magenta",linetype = 2,size = 0.5 )+xlab("研究種目")+ylab("交付額（万円）")+theme_bw(base_family ="yugo")+theme(axis.text.x = element_text(angle = 90, hjust = 1),plot.margin = grid::unit(c(.5, 1, .5, 0), "cm"),panel.grid.major = element_blank(),panel.grid.minor = element_blank(),panel.background = element_blank())
g2

ggdual_axis(lhs = g1, rhs = g2)

url = "http://www.hit-u.ac.jp/guide/information/data/pdf/06_kakenhi_2012.pdf"
url = "day03/06_kakenhi_2012.pdf"
res <- pdf_text(url)
#res<-iconv(res[1],to="UTF-8")
res<-gsub(",","",res[1])
res<-gsub(" +",",",res[1])
df12<-read.csv(text=res[1],skip = 5,header = FALSE,stringsAsFactors = FALSE)
df12<-df12[-(13:nrow(df12)),]

df12$V2[is.na(df12$V2)]<-0
df12$V3[is.na(df12$V3)]<-0
df12$V4[is.na(df12$V4)]<-0

df12$V2<-as.numeric(df12$V2)
df12$V3<-as.numeric(df12$V3)
df12$V4<-as.numeric(df12$V4)
g1<-ggplot(df12,aes(x=V1,y=V2))+geom_bar(stat="identity")+xlab("研究種目")+ylab("交付件数")+theme_gray(base_family ="yugo")+theme(axis.text.x = element_text(angle = 90, hjust = 1),plot.margin = grid::unit(c(.5, 1, .5, 0), "cm"))
g1

g2<-ggplot(df12,aes(x=V1,y=(V3+V4)/10000,group=1))+geom_line(colour = "magenta",linetype = 2,size = 0.5 )+xlab("研究種目")+ylab("交付額（万円）")+theme_bw(base_family ="yugo")+theme(axis.text.x = element_text(angle = 90, hjust = 1),plot.margin = grid::unit(c(.5, 1, .5, 0), "cm"),panel.grid.major = element_blank(),panel.grid.minor = element_blank(),panel.background = element_blank())
g2

ggdual_axis(lhs = g1, rhs = g2)

url = "http://www.hit-u.ac.jp/guide/information/data/pdf/06_kakenhi_2011.pdf"
url = "day03/06_kakenhi_2011.pdf"
res <- pdf_text(url)
#res<-iconv(res[1],to="UTF-8")
res<-gsub(",","",res[1])
res<-gsub(" +",",",res[1])
df11<-read.csv(text=res[1],skip = 5,header = FALSE,stringsAsFactors = FALSE)
df11<-df11[-(15:nrow(df11)),]

df11$V2[is.na(df11$V2)]<-0
df11$V3[is.na(df11$V3)]<-0
df11$V4[is.na(df11$V4)]<-0

df11$V2<-as.numeric(df11$V2)
df11$V3<-as.numeric(df11$V3)
df11$V4<-as.numeric(df11$V4)
g1<-ggplot(df11,aes(x=V1,y=V2))+geom_bar(stat="identity")+xlab("研究種目")+ylab("交付件数")+theme_gray(base_family ="yugo")+theme(axis.text.x = element_text(angle = 90, hjust = 1),plot.margin = grid::unit(c(.5, 1, .5, 0), "cm"))
g1

g2<-ggplot(df11,aes(x=V1,y=(V3+V4)/10000,group=1))+geom_line(colour = "magenta",linetype = 2,size = 0.5 )+xlab("研究種目")+ylab("交付額（万円）")+theme_bw(base_family ="yugo")+theme(axis.text.x = element_text(angle = 90, hjust = 1),plot.margin = grid::unit(c(.5, 1, .5, 0), "cm"),panel.grid.major = element_blank(),panel.grid.minor = element_blank(),panel.background = element_blank())
g2

ggdual_axis(lhs = g1, rhs = g2)

url = "http://www.hit-u.ac.jp/guide/information/data/pdf/06_kakenhi_2010.pdf"
url = "day03/06_kakenhi_2010.pdf"
res <- pdf_text(url)
#res<-iconv(res[1],to="UTF-8")
res<-gsub(",","",res[1])
res<-gsub(" +",",",res[1])
df10<-read.csv(text=res[1],skip = 5,header = FALSE,stringsAsFactors = FALSE)
df10<-df10[-(15:nrow(df10)),]

df10$V2[is.na(df10$V2)]<-0
df10$V3[is.na(df10$V3)]<-0
df10$V4[is.na(df10$V4)]<-0

df10$V2<-as.numeric(df10$V2)
df10$V3<-as.numeric(df10$V3)
df10$V4<-as.numeric(df10$V4)
g1<-ggplot(df10,aes(x=V1,y=V2))+geom_bar(stat="identity")+xlab("研究種目")+ylab("交付件数")+theme_gray(base_family ="yugo")+theme(axis.text.x = element_text(angle = 90, hjust = 1),plot.margin = grid::unit(c(.5, 1, .5, 0), "cm"))
g1

g2<-ggplot(df10,aes(x=V1,y=(V3+V4)/10000,group=1))+geom_line(colour = "magenta",linetype = 2,size = 0.5 )+xlab("研究種目")+ylab("交付額（万円）")+theme_bw(base_family ="yugo")+theme(axis.text.x = element_text(angle = 90, hjust = 1),plot.margin = grid::unit(c(.5, 1, .5, 0), "cm"),panel.grid.major = element_blank(),panel.grid.minor = element_blank(),panel.background = element_blank())
g2

ggdual_axis(lhs = g1, rhs = g2)

url = "http://www.hit-u.ac.jp/guide/information/data/pdf/06_kakenhi_2009.pdf"
url = "day03/06_kakenhi_2009.pdf"
res <- pdf_text(url)
#res<-iconv(res[1],to="UTF-8")
res<-gsub(",","",res[1])
res<-gsub(" +",",",res[1])
df09<-read.csv(text=res[1],skip = 6,header = FALSE,stringsAsFactors = FALSE)
df09<-df09[-(12:nrow(df09)),]

df09$V2[is.na(df09$V2)]<-0
df09$V3[is.na(df09$V3)]<-0
df09$V4[is.na(df09$V4)]<-0
df09$V2<-as.numeric(df09$V2)
df09$V3<-as.numeric(df09$V3)
df09$V4<-as.numeric(df09$V4)

g1<-ggplot(df09,aes(x=V1,y=V2))+geom_bar(stat="identity")+xlab("研究種目")+ylab("交付件数")+theme_gray(base_family ="yugo")+theme(axis.text.x = element_text(angle = 90, hjust = 1),plot.margin = grid::unit(c(.5, 1, .5, 0), "cm"))
g1

g2<-ggplot(df09,aes(x=V1,y=(V3+V4)/10000,group=1))+geom_line(colour = "magenta",linetype = 2,size = 0.5 )+xlab("研究種目")+ylab("交付額（万円）")+theme_bw(base_family ="yugo")+theme(axis.text.x = element_text(angle = 90, hjust = 1),plot.margin = grid::unit(c(.5, 1, .5, 0), "cm"),panel.grid.major = element_blank(),panel.grid.minor = element_blank(),panel.background = element_blank())
g2

ggdual_axis(lhs = g1, rhs = g2)

kaken_c<-cbind(df16[df16$V1=="基盤研究（C）",],year=2016)
kaken_c<-rbind(kaken_c,cbind(df15[df15$V1=="基盤研究（C）",],year=2015))
kaken_c<-rbind(kaken_c,cbind(df14[df14$V1=="基盤研究（C）",],year=2014))
kaken_c<-rbind(kaken_c,cbind(df13[df13$V1=="基盤研究（C）",],year=2013))
kaken_c<-rbind(kaken_c,cbind(df12[df12$V1=="基盤研究（C）",],year=2012))
kaken_c<-rbind(kaken_c,cbind(df11[df11$V1=="基盤研究（C）",],year=2011))
kaken_c<-rbind(kaken_c,cbind(df10[df10$V1=="基盤研究（C）",],year=2010))
kaken_c<-rbind(kaken_c,cbind(df09[df09$V1=="基盤研究（Ｃ）",],year=2009))

colnames(kaken_c)<-c("type","count","direct","indirect","year")
kaken_c$type <- "基盤研究(C)"

g1<-ggplot(kaken_c,aes(x=year,y=count))+geom_bar(stat="identity")+xlab("年")+ylab("件数")+theme_bw(base_family ="yugo")+theme(plot.margin = grid::unit(c(.5, 1, .5, 0), "cm"))
g2<-ggplot(kaken_c,aes(x=year,y=(direct+indirect)/1000))+geom_line(stat="identity")+ylab("経費(千円)")+theme_bw(base_family ="yugo")+theme(plot.margin = grid::unit(c(.5, 1, .5, 0), "cm"),panel.grid.major = element_blank(),panel.grid.minor = element_blank(),panel.background = element_blank())
ggdual_axis(lhs = g1, rhs = g2)

kaken_b<-cbind(df16[df16$V1=="基盤研究（B）",],year=2016)
kaken_b<-rbind(kaken_b,cbind(df15[df15$V1=="基盤研究（B）",],year=2015))
kaken_b<-rbind(kaken_b,cbind(df14[df14$V1=="基盤研究（B）",],year=2014))
kaken_b<-rbind(kaken_b,cbind(df13[df13$V1=="基盤研究（B）",],year=2013))
kaken_b<-rbind(kaken_b,cbind(df12[df12$V1=="基盤研究（B）",],year=2012))
kaken_b<-rbind(kaken_b,cbind(df11[df11$V1=="基盤研究（B）",],year=2011))
kaken_b<-rbind(kaken_b,cbind(df10[df10$V1=="基盤研究（B）",],year=2010))
kaken_b<-rbind(kaken_b,cbind(df09[df09$V1=="基盤研究（Ｂ）",],year=2009))

colnames(kaken_b)<-c("type","count","direct","indirect","year")
kaken_b$type <- "基盤研究(B)"

g1<-ggplot(kaken_b,aes(x=year,y=count))+geom_bar(stat="identity")+xlab("年")+ylab("件数")+theme_bw(base_family ="yugo")+theme(plot.margin = grid::unit(c(.5, 1, .5, 0), "cm"))
g2<-ggplot(kaken_b,aes(x=year,y=((direct+indirect)/1000)))+geom_line(stat="identity")+ylab("経費(千円)")+theme_bw(base_family ="yugo")+theme(plot.margin = grid::unit(c(.5, 1, .5, 0), "cm"),panel.grid.major = element_blank(),panel.grid.minor = element_blank(),panel.background = element_blank())
ggdual_axis(lhs = g1, rhs = g2)

kaken_a<-cbind(df16[df16$V1=="基盤研究（A）",],year=2016)
kaken_a<-rbind(kaken_a,cbind(df15[df15$V1=="基盤研究（A）",],year=2015))
kaken_a<-rbind(kaken_a,cbind(df14[df14$V1=="基盤研究（A）",],year=2014))
kaken_a<-rbind(kaken_a,cbind(df13[df13$V1=="基盤研究（A）",],year=2013))
kaken_a<-rbind(kaken_a,cbind(df12[df12$V1=="基盤研究（A）",],year=2012))
kaken_a<-rbind(kaken_a,cbind(df11[df11$V1=="基盤研究（A）",],year=2011))
kaken_a<-rbind(kaken_a,cbind(df10[df10$V1=="基盤研究（A）",],year=2010))
kaken_a<-rbind(kaken_a,cbind(df09[df09$V1=="基盤研究（Ａ）",],year=2009))

colnames(kaken_a)<-c("type","count","direct","indirect","year")
kaken_a$type <- "基盤研究(A)"

g1<-ggplot(kaken_a,aes(x=year,y=count))+geom_bar(stat="identity")+xlab("年")+ylab("件数")+theme_bw(base_family ="yugo")+theme(plot.margin = grid::unit(c(.5, 1, .5, 0), "cm"))
g2<-ggplot(kaken_a,aes(x=year,y=((direct+indirect)/1000)))+geom_line(stat="identity")+ylab("経費(千円)")+theme_bw(base_family ="yugo")+theme(plot.margin = grid::unit(c(.5, 1, .5, 0), "cm"),panel.grid.major = element_blank(),panel.grid.minor = element_blank(),panel.background = element_blank())
ggdual_axis(lhs = g1, rhs = g2)

kaken_s<-cbind(df16[df16$V1=="基盤研究（S）",],year=2016)
kaken_s<-rbind(kaken_s,cbind(df15[df15$V1=="基盤研究（S）",],year=2015))
kaken_s<-rbind(kaken_s,cbind(df14[df14$V1=="基盤研究（S）",],year=2014))
kaken_s<-rbind(kaken_s,cbind(df13[df13$V1=="基盤研究（S）",],year=2013))
kaken_s<-rbind(kaken_s,cbind(df12[df12$V1=="基盤研究（S）",],year=2012))
kaken_s<-rbind(kaken_s,cbind(df11[df11$V1=="基盤研究（S）",],year=2011))
kaken_s<-rbind(kaken_s,cbind(df10[df10$V1=="基盤研究（S）",],year=2010))
kaken_s<-rbind(kaken_s,cbind(df09[df09$V1=="基盤研究（Ｓ）",],year=2009))

colnames(kaken_s)<-c("type","count","direct","indirect","year")
kaken_s$type <- "基盤研究(S)"

g1<-ggplot(kaken_s,aes(x=year,y=count))+geom_bar(stat="identity")+xlab("年")+ylab("件数")+theme_bw(base_family ="yugo")+theme(plot.margin = grid::unit(c(.5, 1, .5, 0), "cm"))
g2<-ggplot(kaken_s,aes(x=year,y=((direct+indirect)/1000)))+geom_line(stat="identity")+ylab("経費(千円)")+theme_bw(base_family ="yugo")+theme(plot.margin = grid::unit(c(.5, 1, .5, 0), "cm"),panel.grid.major = element_blank(),panel.grid.minor = element_blank(),panel.background = element_blank())
ggdual_axis(lhs = g1, rhs = g2)

kaken <- rbind(kaken_c,kaken_b,kaken_a,kaken_s)
ggplot(kaken,aes(x=year,y=count,fill=type))+geom_bar(stat="identity")+ggtitle("科研費基盤研究：交付件数の推移")+theme_bw(base_family ="yugo")

ggplot(kaken,aes(x=year,y=(direct+indirect)/1000,fill=type))+geom_bar(stat="identity")+ylab("経費(千円)")+ggtitle("科研費基盤研究：交付経費の推移")+theme_bw(base_family ="yugo")

save(list = ls(all.names = TRUE), file = "day03/all.RData")